Content recommendation method and device

Abstract

A content recommendation method and device for recommending content to a user are disclosed. According to one embodiment, the content recommendation device extracts the features of a user from image data, audio data and the like, and can determine a recognition rate indicating the degree that is recognized as a user model predetermined according to the features of the user. The content recommendation device can determine the recommended content to be provided to the user on the basis of the determined recognition rate.

What is claimed is: 
     
       1. A method of recommending contents, the method comprising:
 extracting user features of a user from at least one of image data and audio data; 
 determining, for each of the user features, a recognition rate indicating a degree to which the user is recognized as a first user model; and 
 determining recommendation contents to be provided to the user based on the recognition rate,
 wherein the determining of the recommendation contents comprises: 
 
 determining, when a plurality of user models have a recognition rate included in a range between a first threshold and a second threshold greater than the first threshold and no user model is determined to have a recognition rate greater than the second threshold, preference contents that are common between the plurality of user models as the recommendation contents. 
 
     
     
       2. The method of  claim 1 , further comprising determining a user model corresponding to the user,
 wherein the determining of the user model corresponding to the user includes: 
 determining a weight for each of the user features, 
 determining a final recognition rate for each user model based on the recognition rates determined for the user features and the weights determined for the user features; and 
 determining a user model having a greatest final recognition rate among the final recognition rates determined for the user models to be the user model corresponding to the user. 
 
     
     
       3. The method of  claim 2 , wherein the weight is determined based on at least one of,
 a distance from a camera to the user, or 
 a duration of the determining of the user model. 
 
     
     
       4. The method of  claim 1 , further comprising determining a user mode corresponding to the user,
 wherein the determining of the user model corresponding to the user includes: 
 determining a weight for each of the user features; 
 identifying, with respect to each of the user features, a user model having a recognition rate greater than or equal to the second threshold; determining, for each of the user features, a corresponding user model group such that, 
 for each user feature, the user model group corresponding to the user feature includes models, from among the user models, that have a recognition rate greater than the first threshold and less than the second threshold; and 
 determining the user model corresponding to the user based on, 
 the user models identified with respect to the user features, 
 the user model groups determined for the user features, and 
 the weights determined for the user features. 
 
     
     
       5. The method of  claim 1 , further comprising:
 displaying the recommendation contents. 
 
     
     
       6. The method of  claim 1 , wherein the determining of the recommendation contents includes:
 determining, for each of the user features, one or more user models having a recognition rate included in the range between the first threshold and the second threshold; 
 determining preference contents that are common between the one or more user models determined for each of the user features, when no user model is determined to have a recognition rate greater than the second threshold; 
 outputting a selection request message requesting selection of one of the preference contents that are common between the one or more user modules determined for each of the user features; and 
 determining a user model corresponding to the user based on a selection response message responding to the selection request message and determining preference contents of the determined user model as the recommendation contents to be provided to the user. 
 
     
     
       7. The method of  claim 1 , wherein the user features include at least one of a face, a hairstyle, a height, a body type, a gait, a gender, a complexion, a voice, a sound of footsteps, or clothing of the user. 
     
     
       8. A non-transitory computer-readable medium comprising a program for instructing a computer to perform the method of  claim 1 . 
     
     
       9. A method of recommending contents, the method comprising:
 detecting a presence of a new user based on image data acquired by a camera; 
 determining preference contents for the new user when the new user is present; and 
 providing information on the determined preference contents, 
 wherein the determining of the preference contents comprises: 
 extracting a user feature of the new user; 
 determining a user model corresponding to the new user based on the extracted user feature; and 
 determining, when a plurality of user models corresponding to users including the new user have a recognition rate included in a range between a first threshold and a second threshold greater than the first threshold and no user model is determined to have a recognition rate greater than the second threshold, common preference contents of the plurality of user models as the preference contents for the new user. 
 
     
     
       10. The method of  claim 9 , wherein the providing of the information on the preference contents includes displaying the information using a popup window or playing the preference contents on a portion of a screen. 
     
     
       11. The method of  claim 9 , wherein when the preference contents are played on a portion of a screen, the providing of the information on the preference contents includes determining a transparency of the preference contents based on a recognition degree of the new user. 
     
     
       12. The method of  claim 9 , further comprising:
 suspending playing of current contents and playing the preference contents when a selection request for the preference contents is received. 
 
     
     
       13. A method of recommending contents, the method comprising:
 detecting an absence of one of a plurality of current users based on image data acquired by a camera; 
 determining preference contents for remaining users of the plurality of current users, excluding the current user whose absence was detected, when the absence is detected; and 
 providing information on the determined preference contents, 
 wherein the determining of the preference contents comprises: 
 determining, when a plurality of user models corresponding to the remaining users have a recognition rate included in a range between a first threshold and a second threshold greater than the first threshold and no user model is determined to have a recognition rate greater than the second threshold, common preference contents of the plurality of user models as the preference contents. 
 
     
     
       14. The method of  claim 13 , wherein the providing of the information on the preference contents comprises:
 displaying the information on the preference contents using a popup window or playing the preference contents on a portion of a screen. 
 
     
     
       15. The method of  claim 13 , wherein the providing of the information on the preference contents includes determining a transparency of the preference contents based on a recognition degree of the remaining users, when the preference contents are played on a portion of a screen. 
     
     
       16. The method of  claim 13 , further comprising:
 suspending playing of current contents and playing the preference contents when a selection request for the preference contents is received.